CVE-2026-27829
SSRF via Image Domain Bypass in Astro Framework (v
Publication date: 2026-02-26
Last updated on: 2026-03-09
Assigner: GitHub, Inc.
Description
Description
CVSS Scores
EPSS Scores
| Probability: | |
| Percentile: |
Meta Information
Affected Vendors & Products
| Vendor | Product | Version / Range |
|---|---|---|
| astro | @astrojs/node | From 9.0.0 (inc) to 9.5.4 (exc) |
Helpful Resources
Exploitability
| CWE ID | Description |
|---|---|
| CWE-918 | The web server receives a URL or similar request from an upstream component and retrieves the contents of this URL, but it does not sufficiently ensure that the request is being sent to the expected destination. |
Attack-Flow Graph
AI Powered Q&A
Can you explain this vulnerability to me?
[{'type': 'paragraph', 'content': "CVE-2026-27829 is a Server-Side Request Forgery (SSRF) vulnerability in the Astro web framework versions 9.0.0 through 9.5.3. It occurs because Astro's image pipeline does not enforce domain restrictions when using the inferSize option, which fetches remote images at render time to determine their dimensions."}, {'type': 'paragraph', 'content': 'Normally, Astro restricts remote image fetching to authorized domains specified by the image.domains or image.remotePatterns settings. However, when inferSize is enabled, no domain validation is performed, allowing the server to fetch images from any remote host regardless of these restrictions.'}, {'type': 'paragraph', 'content': 'An attacker who can control the image URL (for example, via CMS content or user input) can exploit this to make the server fetch content from unauthorized or internal hosts, bypassing the configured domain allowlist.'}] [1]
How can this vulnerability impact me? :
This vulnerability allows attackers to bypass domain restrictions and perform SSRF attacks, causing the server to make unauthorized requests to arbitrary hosts.
Potential impacts include accessing internal network services or cloud metadata endpoints that are normally protected, which can lead to unauthorized information disclosure or other malicious actions.
The vulnerability has a moderate severity with a CVSS v3 base score of 6.5, indicating it can affect integrity and availability to a low extent without requiring privileges or user interaction.
How does this vulnerability affect compliance with common standards and regulations (like GDPR, HIPAA)?:
I don't know
How can this vulnerability be detected on my network or system? Can you suggest some commands?
This vulnerability can be detected by monitoring server logs for unexpected outbound requests to unauthorized or internal hosts, especially those triggered by image fetches during render time when the inferSize option is used.
A proof-of-concept involves configuring Astro to allow image fetching only from authorized domains and then checking if requests are still made to unauthorized internal services.
You can use network monitoring tools or commands to detect such unauthorized requests. For example:
- Use tcpdump or Wireshark to capture outgoing HTTP requests from the server and filter for requests to unexpected IP addresses or domains.
- Use curl or wget commands to test if the server fetches images from unauthorized hosts by manipulating image URLs in the application.
- Check application logs for image fetch requests that do not match the configured image.domains or image.remotePatterns.
What immediate steps should I take to mitigate this vulnerability?
The immediate mitigation step is to upgrade the @astrojs/node package to version 9.5.4 or later, where this vulnerability has been fixed.
Until the upgrade is applied, avoid using the inferSize option in the image pipeline, as it bypasses domain restrictions and enables SSRF.
Additionally, review and tighten the image.domains and image.remotePatterns configurations to restrict remote image fetching as much as possible.